{"id":"https://openalex.org/W2970773251","doi":"https://doi.org/10.18653/v1/w19-4607","title":"Arabic Named Entity Recognition: What Works and What\u2019s Next","display_name":"Arabic Named Entity Recognition: What Works and What\u2019s Next","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970773251","doi":"https://doi.org/10.18653/v1/w19-4607","mag":"2970773251"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4607","pdf_url":"https://www.aclweb.org/anthology/W19-4607.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4607.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100657035","display_name":"Liyuan Liu","orcid":"https://orcid.org/0000-0003-2585-323X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liyuan Liu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingbo Shang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100657035"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.1561,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84482164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8210711479187012},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.7610436677932739},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7186882495880127},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6542072892189026},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6200852394104004},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6188386678695679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6057555675506592},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6034510731697083},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5571582913398743},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5211746096611023},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5060839056968689},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4750378429889679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4525338113307953},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43859732151031494},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.42456504702568054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.368678480386734},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.21240460872650146},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10193437337875366},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08428898453712463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210711479187012},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.7610436677932739},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7186882495880127},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6542072892189026},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6200852394104004},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6188386678695679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057555675506592},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6034510731697083},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5571582913398743},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5211746096611023},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5060839056968689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4750378429889679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4525338113307953},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43859732151031494},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.42456504702568054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.368678480386734},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.21240460872650146},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10193437337875366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08428898453712463},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4607","pdf_url":"https://www.aclweb.org/anthology/W19-4607.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4607","pdf_url":"https://www.aclweb.org/anthology/W19-4607.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1346049954","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2104517209","display_name":null,"funder_award_id":"IIS-17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2401976165","display_name":null,"funder_award_id":"GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2490215300","display_name":null,"funder_award_id":"U54GM114838","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3339524276","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3346663007","display_name":null,"funder_award_id":"grant 1U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G427511869","display_name":null,"funder_award_id":"IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4359693134","display_name":null,"funder_award_id":"NIGMS","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G523448137","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7212248142","display_name":null,"funder_award_id":"U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7561134949","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7903051118","display_name":null,"funder_award_id":"IIS 16-18481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8081369098","display_name":null,"funder_award_id":"IIS 16-18481, IIS 17-04532, and IIS-17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8851674072","display_name":null,"funder_award_id":"W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970773251.pdf","grobid_xml":"https://content.openalex.org/works/W2970773251.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1697700638","https://openalex.org/W1940872118","https://openalex.org/W2004763266","https://openalex.org/W2033599040","https://openalex.org/W2045993505","https://openalex.org/W2056451646","https://openalex.org/W2104912629","https://openalex.org/W2147272182","https://openalex.org/W2147880316","https://openalex.org/W2152540201","https://openalex.org/W2250816155","https://openalex.org/W2296283641","https://openalex.org/W2471147443","https://openalex.org/W2493916176","https://openalex.org/W2738180183","https://openalex.org/W2756381707","https://openalex.org/W2773616286","https://openalex.org/W2791193613","https://openalex.org/W2880875857","https://openalex.org/W2882319491","https://openalex.org/W2891383691","https://openalex.org/W2903382683","https://openalex.org/W2950577311","https://openalex.org/W2962676330","https://openalex.org/W2962739339","https://openalex.org/W2962902328","https://openalex.org/W2963558636","https://openalex.org/W2963563735","https://openalex.org/W2963972328"],"related_works":["https://openalex.org/W189110383","https://openalex.org/W2530283981","https://openalex.org/W2589080577","https://openalex.org/W3161409692","https://openalex.org/W4321523623","https://openalex.org/W4287197350","https://openalex.org/W3036779180","https://openalex.org/W2790360088","https://openalex.org/W3035097673","https://openalex.org/W3047727388"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,7,46,78,87,99,103],"winning":[4],"solution":[5],"to":[6,60,98],"Arabic":[8],"Named":[9],"Entity":[10],"Recognition":[11],"challenge":[12],"run":[13],"by":[14,52],"Topcoder.com.":[15],"The":[16,34],"proposed":[17],"model":[18,36],"integrates":[19],"various":[20],"tailored":[21],"techniques":[22],"together,":[23],"including":[24],"representation":[25,72],"learning,":[26],"feature":[27,95],"engineering,":[28],"sequence":[29],"labeling,":[30],"and":[31,49,65,85,108],"ensemble":[32],"learning.":[33],"final":[35],"achieves":[37],"a":[38,53,82],"test":[39],"F":[40],"1":[41,114],"score":[42],"of":[43,102],"75.82%":[44],"on":[45],"AQMAR":[47],"dataset":[48],"outperforms":[50],"baselines":[51],"large":[54],"margin.":[55],"Detailed":[56],"analyses":[57],"are":[58,111],"conducted":[59],"reveal":[61],"both":[62],"its":[63],"strengths":[64],"limitations.":[66],"Specifically,":[67],"we":[68],"observe":[69],"that":[70],"(1)":[71],"learning":[73],"modules":[74],"can":[75,90],"significantly":[76],"boost":[77],"performance":[79],"but":[80],"requires":[81],"proper":[83],"pre-processing":[84],"(2)":[86],"resulting":[88],"embedding":[89],"be":[91],"further":[92],"enhanced":[93],"with":[94],"engineering":[96],"due":[97],"limited":[100],"size":[101],"training":[104],"data.":[105],"All":[106],"implementations":[107],"pre-trained":[109],"models":[110],"made":[112],"public":[113],".":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}